Deep reinforcement learning for robotic manipulation
作者： Shixiang Gu , Sergey Levine , Ethan Holly , Timothy Lillicrap
DOI:
关键词:
摘要: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes for determining robotic action based on current state. Some of those implementations collect experience data from multiple robots operate simultaneously. Each robot generates instances during iterative performance episodes are each explorations performing task, and guided the parameters episode. The collected is generated used by iteratively updating batch data. Further, prior plurality performed robots, updated can be provided (or retrieved) utilization in
arxiv.org
lens.org 参考文章(6)
Volodymyr Mnih, Koray Kavukcuoglu, Methods and apparatus for reinforcement learning ,(2013)
Arun Nair, Charles Beattie, Alessandro De Maria, Rory Fearon, Cagdas Alcicek, Vedavyas Panneershelvam, David Silver, Stig Petersen, Mustafa Suleyman, Sam Blackwell, Praveen Srinivasan, Volodymyr Mnih, Koray Kavukcuoglu, Shane Legg, Massively Parallel Methods for Deep Reinforcement Learning arXiv: Learning. ,(2015)
Stephen L. Thaler, Device for the autonomous bootstrapping of useful information ,(2006)
Volodymyr Mnih, Koray Kavukcuoglu, Arun Sarath Nair, Rory Fearon, Cagdas Alcicek, Vedavyas Panneershelvam, David Silver, Mustafa Suleyman, Samuel Blackwell, Maria Alessandro De, Praveen Deepak Srinivasan, Distributed training of reinforcement learning systems ,(2016)
Chelsea Finn, Sergey Levine, Deirdre Quillen, Ofir Nachum, Julian Ibarz, Eric Jang, Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods arXiv: Robotics. ,(2018)
Sergey Levine, Peter Pastor, Alex Krizhevsky, Julian Ibarz, Deirdre Quillen, Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection The International Journal of Robotics Research. ,vol. 37, pp. 421- 436 ,(2018) , 10.1177/0278364917710318